Data preprocessing
Group 7
2024-03-24
1 TREATMENT
1.1 Import the data:
datos <- read_excel("Base_Pembro_1L_febrero_24__v2.xlsx", sheet = "datos")## New names:
## • `Estudios` -> `Estudios...14`
## • `Est_civil` -> `Est_civil...15`
## • `Comp_hogar` -> `Comp_hogar...16`
## • `MOSs` -> `MOSs...17`
## • `Ansiedad` -> `Ansiedad...18`
## • `Depresion` -> `Depresion...19`
## • `MNA` -> `MNA...20`
## • `MNA` -> `MNA...27`
## • `Estudios` -> `Estudios...29`
## • `Est_civil` -> `Est_civil...31`
## • `Comp_hogar` -> `Comp_hogar...32`
## • `MOSs` -> `MOSs...33`
## • `Ansiedad` -> `Ansiedad...36`
## • `Depresion` -> `Depresion...37`We delete individuals 17 and 21 because of their missing values:
datos <- datos[-c(17, 21), ]1.2 We combine repeated columns:
datos <- datos %>%
mutate(estudios = coalesce(`Estudios...14`, `Estudios...29`)) %>%
select(-`Estudios...14`, -`Estudios...29`)
datos <- datos %>%
mutate(est_civil = coalesce(`Est_civil...15`, `Est_civil...31`)) %>%
select(-`Est_civil...15`, -`Est_civil...31`)
datos <- datos %>%
mutate(hogar = coalesce(`Comp_hogar...16`, `Comp_hogar...32`)) %>%
select(-`Comp_hogar...16`, -`Comp_hogar...32`)
datos <- datos %>%
mutate(MOOSs = coalesce(`MOSs...17`, `MOSs...33`)) %>%
select(-`MOSs...17`, -`MOSs...33`)
datos <- datos %>%
mutate(ansiedad = coalesce(`Ansiedad...18`, `Ansiedad...36`)) %>%
select(-`Ansiedad...18`, -`Ansiedad...36`)
datos <- datos %>%
mutate(depresion = coalesce(`Depresion...19`, `Depresion...37`)) %>%
select(-`Depresion...19`, -`Depresion...37`)
datos <- datos %>%
mutate(MNA = coalesce(`MNA...20`, `MNA...27`)) %>%
select(-`MNA...20`, -`MNA...27`)1.3 We eliminate variables that are not useful:
Elderly variables:
datos <- datos %>% select(-G8, -Audicion, -Barthel, -Lawton_Brody, -SPPB, -Caida_6m, -Pfeiffer, -Mini_mental, -Social_Gijon, -Yesavage,-CIRS, -Charlson,-Polifarmacia,
-Sd_geriatr, -Clasif_geriatr_SIOG1, -Clasif_geriatr_Balducci, -Observaciones, -`CD4+_C_CD45`, -`CD45+_C`, -CD3_C_Leuc, -LDH_PE, -Prot_PE,
-Alb_PE, -Hb_PE, -Leucoc_PE, -Neutr_PE,-Linf_PE, -Plaq_PE, -NLR_PE, -`NLRPE_corte 4`, -`NLRPE_corte 5`, - PLR_PE, -PNI_PE, -SII_PE)Dates:
datos <- datos %>% select(-Fecha_SLP,-Fecha_últ_control,-Fecha_exitus,-Fecha_SG,-Fecha_nac, -Fecha_dx,-Fecha_inicio_pem)Concret variables:
datos <- datos %>% select(-Estado_mut,-Tipo_mut_Tej,-Biopsia_liq,-Tipo_mut_Liq)1.4 Changing of some names:
names(datos)[names(datos) == "Joven(0)_Anciano(1)"] <- "Anciano"
names(datos)[names(datos) == "%_perd_peso"] <- "Porcentaje_perdpeso"
names(datos)[names(datos) == "PD-L1"] <- "PD_L1"
names(datos)[names(datos) == "1ª_eval"] <- "primera_eval"
names(datos)[names(datos) == "1ªeval_num"] <- "primera_eval_num"
names(datos)[names(datos) == "Toxicidad_si/no"] <- "Toxicidad"
names(datos)[names(datos) == "Progresión_sí/no"] <- "Progresion"
names(datos)[names(datos) == "2ªL_sí/no"] <- "segunda_eval"
names(datos)[names(datos) == "Exitus_sí/no"] <- "Exitus"
names(datos)[names(datos) == "T"] <- "Tamaño_tumor"
names(datos)[names(datos) == "N"] <- "Afectacion_ganglionar"
names(datos)[names(datos) == "M"] <- "Afectacion_metastasica"2 STUDY OF MISSING VALUES:
tabla_faltantes = datos %>%
summarise(across(everything(), ~mean(is.na(.)))) %>%
pivot_longer(everything(), names_to = "Columna", values_to = "Porcentaje_NA") %>%
mutate(Porcentaje_NA = Porcentaje_NA * 100)
as.data.frame(tabla_faltantes[order(tabla_faltantes$Porcentaje_NA, decreasing = TRUE),])## Columna Porcentaje_NA
## 1 CD127-/lowFoxP3+_%CD4 91.176471
## 2 CD25+FoxP3+_%Linf 91.176471
## 3 CD39+FoxP3+_%CD4 91.176471
## 4 CD4+_%CD45 91.176471
## 5 CD45+ 91.176471
## 6 CD45RA+_%Linf 91.176471
## 7 CD45RA+FoxP3+_%CD4 91.176471
## 8 Helios+FoxP3+_%CD4 91.176471
## 9 CD127-/lowFoxP3+_C_CD4 91.176471
## 10 CD25+FoxP3+_C_Linf 91.176471
## 11 CD39+FoxP3+_C_CD4 91.176471
## 12 CD45RA+_C_Linf 91.176471
## 13 CD45RA+FoxP3+_C_CD4 91.176471
## 14 Helios+FoxP3+_C_CD4 91.176471
## 15 CD25+CD127low_%Linf 73.529412
## 16 CD25+CD127low_C_Linf 73.529412
## 17 HLADR+Lin_%Leuc 64.705882
## 18 mDC_%Leuc 64.705882
## 19 pDC_%Leuc 64.705882
## 20 CD4_Central_Mem_%Linf 64.705882
## 21 CD4_Effector_Mem_%Linf 64.705882
## 22 CD4_Naïve_%Linf 64.705882
## 23 CD4_TEMRA_%Linf 64.705882
## 24 CD8_Central_Mem_%Linf 64.705882
## 25 CD8_Effector_Mem_%Linf 64.705882
## 26 CD8_Naïve_%Linf 64.705882
## 27 CD8_TEMRA_%Linf 64.705882
## 28 mDC_CD16_%mDC 64.705882
## 29 mDC_CD1c_%mDC 64.705882
## 30 mDC_Clec9A_%mDC 64.705882
## 31 CD3+_%Linf 64.705882
## 32 CD27-CD57+CD3+_%Linf 64.705882
## 33 CD27-CD57+CD4+_%CD3 64.705882
## 34 CD27-CD57+CD8+_%CD3 64.705882
## 35 CD3_%Leuc 64.705882
## 36 CD3+CD4+_%Linf 64.705882
## 37 CD3+CD57+_%Linf 64.705882
## 38 CD3+CD8+_%Linf 64.705882
## 39 CD45RA+CCR7+CD3+_%Linf 64.705882
## 40 CD8+_term_efect_%CD3 64.705882
## 41 CD8_exhausted_%CD3 64.705882
## 42 CD4_TCR_ab+_%CD3 64.705882
## 43 CD4+_%Linf 64.705882
## 44 CD8+_TCR_ab+_%CD3 64.705882
## 45 CD8+_%Linf 64.705882
## 46 CD8+CD4+_%Linf 64.705882
## 47 CD8-CD4-_%Linf 64.705882
## 48 HLADR+CD3+_%Linf 64.705882
## 49 Leuc% 64.705882
## 50 Linf% 64.705882
## 51 TCR_ab+_%Linf 64.705882
## 52 TCR_gd+_%Linf 64.705882
## 53 gd_VD1+_%CD3 64.705882
## 54 gd_VD1+VD2+_%CD3 64.705882
## 55 gd_VD1-VD2-_%CD3 64.705882
## 56 gd_VD2+_%CD3 64.705882
## 57 CD25+CD4+_%Linf 61.764706
## 58 HLADR+Lin_C_Leuc 61.764706
## 59 mDC_C_Leuc 61.764706
## 60 pDC_C_Leuc 61.764706
## 61 CD4_Central_Mem_C_Linf 61.764706
## 62 CD4_Effector_Mem_C_Linf 61.764706
## 63 CD4_Naïve_C_Linf 61.764706
## 64 CD4_TEMRA_C_Linf 61.764706
## 65 CD8_Central_Mem_C_Linf 61.764706
## 66 CD8_Effector_Mem_C_Linf 61.764706
## 67 CD8_Naïve_C_Linf 61.764706
## 68 CD8_TEMRA_C_Linf 61.764706
## 69 mDC_CD16_C_mDC 61.764706
## 70 mDC_CD1c_C_mDC 61.764706
## 71 mDC_Clec9A_C_mDC 61.764706
## 72 CD3+_C_Linf 61.764706
## 73 CD27-CD57+CD3+_C_Linf 61.764706
## 74 CD27-CD57+CD4+_C_CD3 61.764706
## 75 CD27-CD57+CD8+_C_CD3 61.764706
## 76 CD3+CD4+_C_Linf 61.764706
## 77 CD3+CD57+_C_Linf 61.764706
## 78 CD3+CD8+_C_Linf 61.764706
## 79 CD45RA+CCR7+CD3+_C_Linf 61.764706
## 80 CD8+_term_efect_C_CD3 61.764706
## 81 CD8_exhausted_C_CD3 61.764706
## 82 CD4_TCR_ab+_C_CD3 61.764706
## 83 CD4+_C_Linf 61.764706
## 84 CD8+_TCR_ab+_C_CD3 61.764706
## 85 CD8+_C_Linf 61.764706
## 86 CD8+CD4+_C_Linf 61.764706
## 87 CD8-CD4-_C_Linf 61.764706
## 88 HLADR+CD3+_C_Linf 61.764706
## 89 TCR_ab+_C_Linf 61.764706
## 90 TCR_gd+_C_Linf 61.764706
## 91 gd_VD1+_C_CD3 61.764706
## 92 gd_VD1+VD2+_C_CD3 61.764706
## 93 gd_VD1-VD2-_C_CD3 61.764706
## 94 gd_VD2+_C_CD3 61.764706
## 95 CD25+CD4+_C_Linf 61.764706
## 96 MOOSs 61.764706
## 97 IL-6 58.823529
## 98 IgM_CMV 55.882353
## 99 IgG_CMV 55.882353
## 100 Col_LDL 47.058824
## 101 LDH_2C 47.058824
## 102 MNA 47.058824
## 103 ansiedad 44.117647
## 104 depresion 44.117647
## 105 Col_HDL 41.176471
## 106 Fecha_progresión 38.235294
## 107 Num_pac 35.294118
## 108 LDH_1C 35.294118
## 109 LDH_1eval 29.411765
## 110 LinfT_cel 26.470588
## 111 LinfT_% 26.470588
## 112 CD4_cel 26.470588
## 113 CD4_% 26.470588
## 114 CD8_cel 26.470588
## 115 CD8_% 26.470588
## 116 CD4:CD8 26.470588
## 117 LinfB_cel 26.470588
## 118 LinfB_% 26.470588
## 119 LinfNK_cel 26.470588
## 120 LinfNK_% 26.470588
## 121 estudios 26.470588
## 122 est_civil 26.470588
## 123 PCR 23.529412
## 124 hogar 23.529412
## 125 segunda_eval 20.588235
## 126 Prot_2C 11.764706
## 127 Tipo_tox 11.764706
## 128 Porcentaje_perdpeso 8.823529
## 129 p_peso_no_sí 8.823529
## 130 LDH 8.823529
## 131 Prot_1C 8.823529
## 132 Alb_2C 8.823529
## 133 PNI_2C 8.823529
## 134 Prot_1eval 8.823529
## 135 Hab_tabaq 5.882353
## 136 Exp_tab 5.882353
## 137 Alb_1C 5.882353
## 138 Hb_2C 5.882353
## 139 Leucoc_2C 5.882353
## 140 Neutr_2C 5.882353
## 141 Linf_2C 5.882353
## 142 Plaq_2C 5.882353
## 143 NLR_2C 5.882353
## 144 NLR2C_corte4o5 5.882353
## 145 PLR_2C 5.882353
## 146 SII_2C 5.882353
## 147 Tamaño_tumor 2.941176
## 148 Afectacion_ganglionar 2.941176
## 149 Afectacion_metastasica 2.941176
## 150 Col_total 2.941176
## 151 Prot_tot 2.941176
## 152 Albumina 2.941176
## 153 PNI_pre 2.941176
## 154 ALI_pre 2.941176
## 155 NLR1C_corte5 2.941176
## 156 PNI_1C 2.941176
## 157 Idpac 0.000000
## 158 Sexo 0.000000
## 159 Edad_dx 0.000000
## 160 Anciano 0.000000
## 161 ECOG 0.000000
## 162 Peso 0.000000
## 163 Talla 0.000000
## 164 IMC 0.000000
## 165 Diabetes 0.000000
## 166 Cardiop 0.000000
## 167 Enf_neurod 0.000000
## 168 Histologia 0.000000
## 169 Histología_num 0.000000
## 170 Estadio 0.000000
## 171 Estadio_num 0.000000
## 172 PD_L1 0.000000
## 173 Estatinas 0.000000
## 174 Hb 0.000000
## 175 Leucoc_tot 0.000000
## 176 Neutrofilos 0.000000
## 177 Linf_tot 0.000000
## 178 Plaquetas 0.000000
## 179 NLR_pre 0.000000
## 180 PLR_pre 0.000000
## 181 SII_pre 0.000000
## 182 Hb_1C 0.000000
## 183 Leucoc_1C 0.000000
## 184 Neutr_1C 0.000000
## 185 Linf_1C 0.000000
## 186 Plaq_1C 0.000000
## 187 NLR_1C 0.000000
## 188 NLR1C_corte4 0.000000
## 189 PLR_1C 0.000000
## 190 SII_1C 0.000000
## 191 primera_eval 0.000000
## 192 primera_eval_num 0.000000
## 193 Alb_1eval 0.000000
## 194 Hb_1eval 0.000000
## 195 Leucoc_1eval 0.000000
## 196 Neutr_1eval 0.000000
## 197 Linf_1eval 0.000000
## 198 Plaq_1eval 0.000000
## 199 NLR_1eval 0.000000
## 200 PLR_1eval 0.000000
## 201 PNI_1eval 0.000000
## 202 SII_1eval 0.000000
## 203 Mejor_resp 0.000000
## 204 Mejor_resp_num 0.000000
## 205 N_ciclos 0.000000
## 206 Toxicidad 0.000000
## 207 Grado_tox 0.000000
## 208 Interrupc_tto 0.000000
## 209 Motivo_inter 0.000000
## 210 Progresion 0.000000
## 211 Exitus 0.000000
## 212 SLP 0.000000
## 213 SLP_cens 0.000000
## 214 SG 0.000000
## 215 SG_cens 0.000000Our limit is 23%, so we eliminate that variables that overcome the limit.
variables_a_eliminar <- tabla_faltantes %>%
filter(Porcentaje_NA > 23) %>%
pull(Columna)
df <- datos %>%
select(-one_of(variables_a_eliminar))tabla_faltantes = df %>%
summarise(across(everything(), ~mean(is.na(.)))) %>%
pivot_longer(everything(), names_to = "Columna", values_to = "Porcentaje_NA") %>%
mutate(Porcentaje_NA = Porcentaje_NA * 100)
as.data.frame(tabla_faltantes[order(tabla_faltantes$Porcentaje_NA, decreasing = TRUE),])## Columna Porcentaje_NA
## 1 segunda_eval 20.588235
## 2 Prot_2C 11.764706
## 3 Tipo_tox 11.764706
## 4 Porcentaje_perdpeso 8.823529
## 5 p_peso_no_sí 8.823529
## 6 LDH 8.823529
## 7 Prot_1C 8.823529
## 8 Alb_2C 8.823529
## 9 PNI_2C 8.823529
## 10 Prot_1eval 8.823529
## 11 Hab_tabaq 5.882353
## 12 Exp_tab 5.882353
## 13 Alb_1C 5.882353
## 14 Hb_2C 5.882353
## 15 Leucoc_2C 5.882353
## 16 Neutr_2C 5.882353
## 17 Linf_2C 5.882353
## 18 Plaq_2C 5.882353
## 19 NLR_2C 5.882353
## 20 NLR2C_corte4o5 5.882353
## 21 PLR_2C 5.882353
## 22 SII_2C 5.882353
## 23 Tamaño_tumor 2.941176
## 24 Afectacion_ganglionar 2.941176
## 25 Afectacion_metastasica 2.941176
## 26 Col_total 2.941176
## 27 Prot_tot 2.941176
## 28 Albumina 2.941176
## 29 PNI_pre 2.941176
## 30 ALI_pre 2.941176
## 31 NLR1C_corte5 2.941176
## 32 PNI_1C 2.941176
## 33 Idpac 0.000000
## 34 Sexo 0.000000
## 35 Edad_dx 0.000000
## 36 Anciano 0.000000
## 37 ECOG 0.000000
## 38 Peso 0.000000
## 39 Talla 0.000000
## 40 IMC 0.000000
## 41 Diabetes 0.000000
## 42 Cardiop 0.000000
## 43 Enf_neurod 0.000000
## 44 Histologia 0.000000
## 45 Histología_num 0.000000
## 46 Estadio 0.000000
## 47 Estadio_num 0.000000
## 48 PD_L1 0.000000
## 49 Estatinas 0.000000
## 50 Hb 0.000000
## 51 Leucoc_tot 0.000000
## 52 Neutrofilos 0.000000
## 53 Linf_tot 0.000000
## 54 Plaquetas 0.000000
## 55 NLR_pre 0.000000
## 56 PLR_pre 0.000000
## 57 SII_pre 0.000000
## 58 Hb_1C 0.000000
## 59 Leucoc_1C 0.000000
## 60 Neutr_1C 0.000000
## 61 Linf_1C 0.000000
## 62 Plaq_1C 0.000000
## 63 NLR_1C 0.000000
## 64 NLR1C_corte4 0.000000
## 65 PLR_1C 0.000000
## 66 SII_1C 0.000000
## 67 primera_eval 0.000000
## 68 primera_eval_num 0.000000
## 69 Alb_1eval 0.000000
## 70 Hb_1eval 0.000000
## 71 Leucoc_1eval 0.000000
## 72 Neutr_1eval 0.000000
## 73 Linf_1eval 0.000000
## 74 Plaq_1eval 0.000000
## 75 NLR_1eval 0.000000
## 76 PLR_1eval 0.000000
## 77 PNI_1eval 0.000000
## 78 SII_1eval 0.000000
## 79 Mejor_resp 0.000000
## 80 Mejor_resp_num 0.000000
## 81 N_ciclos 0.000000
## 82 Toxicidad 0.000000
## 83 Grado_tox 0.000000
## 84 Interrupc_tto 0.000000
## 85 Motivo_inter 0.000000
## 86 Progresion 0.000000
## 87 Exitus 0.000000
## 88 SLP 0.000000
## 89 SLP_cens 0.000000
## 90 SG 0.000000
## 91 SG_cens 0.0000003 IMPUTATION:
We are going to use library mice.
tipos_var <- data.frame(Columna = names(df))
tipos_var$Tipo <- sapply(df, function(x) class(x)[1])
tipos_var## Columna Tipo
## 1 Idpac character
## 2 Sexo numeric
## 3 Edad_dx numeric
## 4 Anciano numeric
## 5 ECOG numeric
## 6 Peso numeric
## 7 Talla numeric
## 8 IMC numeric
## 9 Porcentaje_perdpeso numeric
## 10 p_peso_no_sí numeric
## 11 Hab_tabaq numeric
## 12 Exp_tab numeric
## 13 Diabetes numeric
## 14 Cardiop numeric
## 15 Enf_neurod numeric
## 16 Histologia character
## 17 Histología_num numeric
## 18 Tamaño_tumor character
## 19 Afectacion_ganglionar character
## 20 Afectacion_metastasica character
## 21 Estadio character
## 22 Estadio_num numeric
## 23 PD_L1 numeric
## 24 Estatinas character
## 25 Col_total numeric
## 26 LDH numeric
## 27 Prot_tot numeric
## 28 Albumina numeric
## 29 Hb numeric
## 30 Leucoc_tot numeric
## 31 Neutrofilos numeric
## 32 Linf_tot numeric
## 33 Plaquetas numeric
## 34 NLR_pre numeric
## 35 PLR_pre numeric
## 36 PNI_pre numeric
## 37 ALI_pre numeric
## 38 SII_pre numeric
## 39 Prot_1C numeric
## 40 Alb_1C numeric
## 41 Hb_1C numeric
## 42 Leucoc_1C numeric
## 43 Neutr_1C numeric
## 44 Linf_1C numeric
## 45 Plaq_1C numeric
## 46 NLR_1C numeric
## 47 NLR1C_corte4 numeric
## 48 NLR1C_corte5 numeric
## 49 PLR_1C numeric
## 50 PNI_1C numeric
## 51 SII_1C numeric
## 52 Prot_2C numeric
## 53 Alb_2C numeric
## 54 Hb_2C numeric
## 55 Leucoc_2C numeric
## 56 Neutr_2C numeric
## 57 Linf_2C numeric
## 58 Plaq_2C numeric
## 59 NLR_2C numeric
## 60 NLR2C_corte4o5 numeric
## 61 PLR_2C numeric
## 62 PNI_2C numeric
## 63 SII_2C numeric
## 64 primera_eval character
## 65 primera_eval_num numeric
## 66 Prot_1eval numeric
## 67 Alb_1eval numeric
## 68 Hb_1eval numeric
## 69 Leucoc_1eval numeric
## 70 Neutr_1eval numeric
## 71 Linf_1eval numeric
## 72 Plaq_1eval numeric
## 73 NLR_1eval numeric
## 74 PLR_1eval numeric
## 75 PNI_1eval numeric
## 76 SII_1eval numeric
## 77 Mejor_resp character
## 78 Mejor_resp_num numeric
## 79 N_ciclos numeric
## 80 Toxicidad numeric
## 81 Tipo_tox character
## 82 Grado_tox character
## 83 Interrupc_tto numeric
## 84 Motivo_inter character
## 85 Progresion numeric
## 86 segunda_eval numeric
## 87 Exitus numeric
## 88 SLP numeric
## 89 SLP_cens numeric
## 90 SG numeric
## 91 SG_cens numericAs we can see, we have both numerical and categorical variables, so we are interested in transforming these categorical variables into factors to be able to impute, even some numerical variables, through the mean method.
df$Idpac <- as.factor(df$Idpac)
df$Histologia <- as.factor(df$Histologia)
df$Tamaño_tumor <- as.factor(df$Tamaño_tumor)
df$Afectacion_ganglionar <- as.factor(df$Afectacion_ganglionar)
df$Afectacion_metastasica <- as.factor(df$Afectacion_metastasica)
df$Estadio <- as.factor(df$Estadio)
df$Estatinas <- as.factor(df$Estatinas)
df$primera_eval_num <- as.factor(df$primera_eval_num)
df$Mejor_resp_num <- as.factor(df$Mejor_resp_num)
df$Tipo_tox <- as.factor(df$Tipo_tox)
df$Grado_tox <- as.factor(df$Grado_tox)
df$Motivo_inter <- as.factor(df$Motivo_inter)
df$p_peso_no_sí <- as.factor(df$p_peso_no_sí)
df$Hab_tabaq <- as.factor(df$Hab_tabaq)
df$NLR1C_corte4 <- as.factor(df$NLR1C_corte4)
df$NLR1C_corte5 <- as.factor(df$NLR1C_corte5)
df$Histología_num <- as.factor(df$Histología_num)
df$Estadio_num <- as.factor(df$Estadio_num)
df$Toxicidad <- as.factor(df$Toxicidad)
df$Interrupc_tto <- as.factor(df$Interrupc_tto)
df$Enf_neurod <- as.factor(df$Enf_neurod)
df$Sexo <- as.factor(df$Sexo)
df$ECOG <- as.factor(df$ECOG)
df$Progresion <- as.factor(df$Progresion)
df$Cardiop <- as.factor(df$Cardiop)
df$Diabetes <- as.factor(df$Diabetes)tipos_var2 <- data.frame(Columna = names(df))
tipos_var2$Tipo <- sapply(df, function(x) class(x)[1])
tipos_var2## Columna Tipo
## 1 Idpac factor
## 2 Sexo factor
## 3 Edad_dx numeric
## 4 Anciano numeric
## 5 ECOG factor
## 6 Peso numeric
## 7 Talla numeric
## 8 IMC numeric
## 9 Porcentaje_perdpeso numeric
## 10 p_peso_no_sí factor
## 11 Hab_tabaq factor
## 12 Exp_tab numeric
## 13 Diabetes factor
## 14 Cardiop factor
## 15 Enf_neurod factor
## 16 Histologia factor
## 17 Histología_num factor
## 18 Tamaño_tumor factor
## 19 Afectacion_ganglionar factor
## 20 Afectacion_metastasica factor
## 21 Estadio factor
## 22 Estadio_num factor
## 23 PD_L1 numeric
## 24 Estatinas factor
## 25 Col_total numeric
## 26 LDH numeric
## 27 Prot_tot numeric
## 28 Albumina numeric
## 29 Hb numeric
## 30 Leucoc_tot numeric
## 31 Neutrofilos numeric
## 32 Linf_tot numeric
## 33 Plaquetas numeric
## 34 NLR_pre numeric
## 35 PLR_pre numeric
## 36 PNI_pre numeric
## 37 ALI_pre numeric
## 38 SII_pre numeric
## 39 Prot_1C numeric
## 40 Alb_1C numeric
## 41 Hb_1C numeric
## 42 Leucoc_1C numeric
## 43 Neutr_1C numeric
## 44 Linf_1C numeric
## 45 Plaq_1C numeric
## 46 NLR_1C numeric
## 47 NLR1C_corte4 factor
## 48 NLR1C_corte5 factor
## 49 PLR_1C numeric
## 50 PNI_1C numeric
## 51 SII_1C numeric
## 52 Prot_2C numeric
## 53 Alb_2C numeric
## 54 Hb_2C numeric
## 55 Leucoc_2C numeric
## 56 Neutr_2C numeric
## 57 Linf_2C numeric
## 58 Plaq_2C numeric
## 59 NLR_2C numeric
## 60 NLR2C_corte4o5 numeric
## 61 PLR_2C numeric
## 62 PNI_2C numeric
## 63 SII_2C numeric
## 64 primera_eval character
## 65 primera_eval_num factor
## 66 Prot_1eval numeric
## 67 Alb_1eval numeric
## 68 Hb_1eval numeric
## 69 Leucoc_1eval numeric
## 70 Neutr_1eval numeric
## 71 Linf_1eval numeric
## 72 Plaq_1eval numeric
## 73 NLR_1eval numeric
## 74 PLR_1eval numeric
## 75 PNI_1eval numeric
## 76 SII_1eval numeric
## 77 Mejor_resp character
## 78 Mejor_resp_num factor
## 79 N_ciclos numeric
## 80 Toxicidad factor
## 81 Tipo_tox factor
## 82 Grado_tox factor
## 83 Interrupc_tto factor
## 84 Motivo_inter factor
## 85 Progresion factor
## 86 segunda_eval numeric
## 87 Exitus numeric
## 88 SLP numeric
## 89 SLP_cens numeric
## 90 SG numeric
## 91 SG_cens numericWe can see the distribution of missing values:
patrones = md.pattern(df, rotate.names = TRUE)
3.1 Mean method:
imputed_data1 <- mice(df %>%
select(-Idpac,-Histologia,-Afectacion_ganglionar, -Afectacion_metastasica,-Estadio,-Estatinas,-primera_eval_num, -Mejor_resp_num,
-Tipo_tox, -Tamaño_tumor, -Grado_tox, -Motivo_inter, -p_peso_no_sí, -Hab_tabaq, -NLR1C_corte4, -NLR1C_corte5,-Histología_num,
-Estadio_num, -Toxicidad,-Interrupc_tto,-Enf_neurod,-Sexo,-ECOG, -Progresion, -Cardiop, -Diabetes),
method = "mean", print = FALSE)## Warning: Number of logged events: 752df_imputado1 <- complete(imputed_data1)
df_imputado1## Edad_dx Anciano Peso Talla IMC Porcentaje_perdpeso Exp_tab PD_L1
## 1 46.00000 0 88.0 1.77 28.08899 0.04583871 20.00000 100
## 2 68.00000 0 85.0 1.55 35.37981 0.00000000 0.00000 70
## 3 59.00000 0 65.0 1.59 25.71101 0.00000000 45.00000 50
## 4 72.00000 1 88.5 1.77 28.24859 0.00000000 92.00000 2
## 5 50.00000 0 90.0 1.76 29.05475 0.10000000 55.00000 60
## 6 71.00000 1 76.6 1.63 28.83059 0.00000000 200.00000 90
## 7 71.00000 1 67.0 1.50 29.77778 0.07600000 60.00000 100
## 8 79.00000 1 67.0 1.61 25.84777 0.00000000 40.00000 70
## 9 73.14168 1 63.0 1.68 22.32143 0.04583871 50.00000 90
## 10 68.51745 0 77.5 1.81 23.65618 0.00000000 50.00000 70
## 11 56.48734 0 73.8 1.75 24.09796 0.04583871 36.00000 80
## 12 66.27242 0 66.3 1.63 24.95389 0.22900000 50.00000 50
## 13 61.96304 0 63.8 1.56 26.21631 0.13800000 0.00000 80
## 14 64.45996 0 65.0 1.79 20.28651 0.11000000 50.00000 100
## 15 58.70500 0 53.0 1.55 22.06035 0.00000000 25.00000 95
## 16 60.30664 0 72.0 1.71 24.62296 0.00000000 82.00000 90
## 17 63.00000 0 67.0 1.50 29.77778 0.00000000 60.00000 100
## 18 82.00000 1 61.0 1.63 22.95909 0.00000000 100.00000 90
## 19 66.00000 0 64.2 1.61 24.76756 0.00000000 50.00000 60
## 20 50.00000 0 55.0 1.63 20.70082 0.00000000 51.65625 100
## 21 78.00000 1 69.0 1.55 28.72008 0.06700000 75.00000 70
## 22 73.00000 1 102.0 1.91 27.95976 0.01000000 83.00000 70
## 23 60.00000 0 67.0 1.73 22.38631 0.13000000 40.00000 100
## 24 70.00000 1 64.7 1.60 25.27344 0.03000000 51.65625 90
## 25 64.00000 0 47.0 1.60 18.35937 0.03100000 40.00000 70
## 26 57.00000 0 61.0 1.62 23.24341 0.04000000 30.00000 70
## 27 71.00000 1 52.0 1.56 21.36752 0.05500000 0.00000 80
## 28 75.00000 1 62.0 1.60 24.21875 0.08800000 25.00000 100
## 29 68.00000 0 75.0 1.68 26.57313 0.03800000 40.00000 90
## 30 62.00000 0 80.0 1.72 27.04164 0.00000000 60.00000 90
## 31 51.00000 0 62.0 1.81 18.92494 0.07500000 45.00000 60
## 32 80.00000 1 53.0 1.58 21.23057 0.15900000 40.00000 80
## 33 65.00000 0 85.0 1.65 31.22130 0.04500000 85.00000 95
## 34 62.00000 0 97.0 1.65 35.62902 0.00000000 25.00000 70
## Col_total LDH Prot_tot Albumina Hb Leucoc_tot Neutrofilos Linf_tot
## 1 217.0000 163.0000 7.000000 4.100000 15.3 10100 8000 1400
## 2 154.0000 171.0000 6.000000 3.700000 11.8 9800 8200 800
## 3 146.0000 197.0000 7.200000 4.300000 16.7 9900 7400 1400
## 4 149.0000 159.0000 7.100000 4.000000 14.6 5600 3000 1800
## 5 210.0000 198.0000 7.900000 4.400000 15.7 8900 5300 2300
## 6 162.0000 220.0000 8.000000 4.300000 13.1 8800 6000 1600
## 7 142.0000 198.0000 6.400000 3.600000 11.5 10000 9000 400
## 8 167.0000 184.0000 7.000000 3.900000 12.3 7700 5300 1600
## 9 153.0000 176.0000 6.900000 3.700000 12.9 16200 13200 1900
## 10 132.0000 199.0000 7.300000 4.000000 13.0 15700 13400 1400
## 11 113.0000 190.0000 7.300000 3.500000 13.6 10600 8000 1500
## 12 182.0000 198.0000 6.500000 3.700000 11.4 8700 5000 2500
## 13 242.0000 184.0000 7.300000 4.100000 13.7 12600 8700 2200
## 14 133.0000 183.0000 7.000000 4.100000 13.7 11400 7600 2300
## 15 215.0000 204.0000 7.200000 4.400000 11.9 13400 9400 2900
## 16 202.0000 276.0000 5.600000 3.200000 15.5 13100 12300 500
## 17 262.0000 201.0000 5.400000 2.800000 11.6 4100 2500 800
## 18 200.0000 383.0000 8.900000 3.900000 12.1 11700 7100 2700
## 19 199.0000 382.0000 6.300000 3.700000 10.6 4000 2600 900
## 20 194.0000 156.0000 7.300000 4.300000 11.5 10800 9400 500
## 21 176.0000 175.0000 7.100000 4.300000 11.5 10600 7300 1200
## 22 160.0000 195.0000 7.300000 4.100000 12.6 7700 4800 1900
## 23 111.0000 326.0000 6.400000 3.000000 13.5 6800 5400 700
## 24 276.0000 263.6452 7.000000 3.900000 14.1 6000 3500 2000
## 25 155.0000 1644.0000 6.900000 3.400000 10.9 13800 8700 3000
## 26 197.0000 279.0000 6.900000 4.400000 13.0 6300 4300 1100
## 27 206.0000 164.0000 6.600000 4.000000 14.0 6200 4800 800
## 28 208.0000 222.0000 7.400000 4.100000 12.4 7200 4900 1500
## 29 191.0000 267.0000 6.900000 3.500000 14.5 20500 11500 3300
## 30 201.0000 248.0000 7.300000 4.200000 13.6 14100 8400 3500
## 31 142.0000 263.6452 7.100000 3.900000 12.8 9600 7100 1300
## 32 187.4545 263.6452 7.006061 3.912121 12.6 7600 5300 1300
## 33 192.0000 230.0000 7.700000 4.400000 15.3 8400 5400 1800
## 34 397.0000 201.0000 7.000000 4.200000 14.2 12500 10700 1300
## Plaquetas NLR_pre PLR_pre PNI_pre ALI_pre SII_pre Prot_1C Alb_1C
## 1 273000 5.714286 195.00000 48.00000 20.153851 1560000.0 7.500000 4.60000
## 2 124000 10.250000 155.00000 41.00000 12.771249 1271000.0 6.200000 3.90000
## 3 349000 5.285714 249.28571 50.00000 20.916253 1844714.3 7.200000 4.40000
## 4 220000 1.666667 122.22222 49.00000 67.796610 366666.7 7.048387 3.90625
## 5 350000 2.304348 152.17391 55.50000 55.478130 806521.7 7.400000 4.50000
## 6 279000 3.750000 174.37500 51.00000 33.059079 1046250.0 8.100000 4.20000
## 7 269000 22.500000 672.50000 38.00000 4.764444 6052500.0 6.500000 4.00000
## 8 201000 3.312500 125.62500 47.00000 30.432089 665812.5 7.700000 4.00000
## 9 317000 6.947368 166.84211 46.50000 11.887852 2202315.8 7.048387 3.90000
## 10 324000 9.571429 231.42857 47.00000 9.886163 3101142.9 7.400000 4.00000
## 11 489000 5.333333 326.00000 42.50000 15.814286 2608000.0 7.000000 3.40000
## 12 216000 2.000000 86.40000 49.50000 46.164703 432000.0 7.100000 4.10000
## 13 455000 3.954545 206.81818 52.00000 27.180583 1799318.2 7.300000 4.00000
## 14 274000 3.304348 119.13043 52.50000 25.171285 905391.3 7.000000 3.70000
## 15 208000 3.241379 71.72414 58.50000 29.945757 674206.9 6.900000 3.70000
## 16 112000 24.600000 224.00000 34.50000 3.202987 2755200.0 7.800000 4.20000
## 17 293000 3.125000 366.25000 32.00000 26.680889 915625.0 4.600000 3.10000
## 18 358000 2.629630 132.59259 52.50000 34.050591 941407.4 9.100000 4.00000
## 19 338000 2.888889 375.55556 41.50000 31.721533 976444.4 6.000000 3.10000
## 20 464000 18.800000 928.00000 45.50000 4.734761 8723200.0 8.000000 4.50000
## 21 158000 6.083333 131.66667 49.00000 20.300771 961166.7 7.200000 4.20000
## 22 248000 2.526316 130.52632 50.50000 45.376360 626526.3 7.300000 3.80000
## 23 335000 7.714286 478.57143 33.50000 8.705789 2584285.7 6.800000 3.60000
## 24 143000 1.750000 71.50000 49.00000 56.323661 250250.0 7.400000 3.90000
## 25 709000 2.900000 236.33333 49.00000 21.524784 2056100.0 7.300000 3.60000
## 26 287000 3.909091 260.90909 49.50000 26.162348 1121909.1 6.400000 3.70000
## 27 295000 6.000000 368.75000 44.00000 14.245014 1770000.0 6.900000 4.10000
## 28 228000 3.266667 152.00000 48.50000 30.397003 744800.0 7.100000 4.00000
## 29 271000 3.484848 82.12121 51.50000 26.688665 944393.9 6.800000 3.30000
## 30 461000 2.400000 131.71429 59.50000 47.322877 1106400.0 6.300000 3.80000
## 31 327000 5.461538 251.53846 45.50000 13.514007 1785923.1 6.500000 3.30000
## 32 249000 4.076923 191.53846 47.42424 26.858982 1015153.8 7.100000 4.30000
## 33 306000 3.000000 170.00000 53.00000 45.791246 918000.0 7.048387 3.90625
## 34 234000 8.230769 180.00000 48.50000 18.180788 1926000.0 6.600000 4.10000
## Hb_1C Leucoc_1C Neutr_1C Linf_1C Plaq_1C NLR_1C PLR_1C PNI_1C
## 1 15.9 8100 6000 1600 369000 3.750000 230.62500 54.00000
## 2 11.7 8500 7000 800 112000 8.750000 140.00000 43.00000
## 3 16.1 12000 8000 2500 382000 3.200000 152.80000 56.50000
## 4 15.5 7300 4400 2000 266000 2.200000 133.00000 10.00000
## 5 15.9 9200 4900 3100 364000 1.580645 117.41935 60.50000
## 6 14.5 8000 5300 1600 293000 3.312500 183.12500 50.00000
## 7 11.6 4500 3200 900 218000 3.555556 242.22222 44.50000
## 8 12.1 3600 1900 900 131000 2.111111 145.55556 44.50000
## 9 14.5 16100 12100 2900 380000 4.172414 131.03448 53.50000
## 10 13.5 12800 9800 1900 214000 5.157895 112.63158 49.50000
## 11 11.4 12500 10400 1000 463000 10.400000 463.00000 39.00000
## 12 11.6 7600 3700 2900 242000 1.275862 83.44828 55.50000
## 13 14.3 11300 6200 3600 452000 1.722222 125.55556 58.00000
## 14 10.8 15400 11300 2500 444000 4.520000 177.60000 49.50000
## 15 11.3 10400 8400 1000 272000 8.400000 272.00000 42.00000
## 16 13.7 14100 9700 3100 494000 3.129032 159.35484 57.50000
## 17 8.4 4800 3300 700 226000 4.714286 322.85714 34.50000
## 18 11.9 11100 6000 3000 380000 2.000000 126.66667 55.00000
## 19 11.1 3600 1700 1100 338000 1.545455 307.27273 36.50000
## 20 11.9 10900 8900 1200 465000 7.416667 387.50000 51.00000
## 21 10.2 13800 9300 1600 205000 5.812500 128.12500 50.00000
## 22 12.5 7400 4600 1800 304000 2.555556 168.88889 47.00000
## 23 16.0 4600 3000 1100 274000 2.727273 249.09091 41.50000
## 24 12.9 6000 3000 2200 277000 1.363636 125.90909 50.00000
## 25 11.1 12600 7000 3600 650000 1.944444 180.55556 54.00000
## 26 11.7 9000 6300 800 457000 7.875000 571.25000 41.00000
## 27 13.6 4900 2700 1600 192000 1.687500 120.00000 49.00000
## 28 11.7 6900 5900 600 259000 9.833333 431.66667 43.00000
## 29 14.5 12800 6800 2800 366000 2.428571 130.71429 47.00000
## 30 11.6 8700 4600 2200 553000 2.090909 251.36364 49.00000
## 31 10.5 9000 6300 1200 513000 5.250000 427.50000 39.00000
## 32 13.2 13100 8700 2900 345000 3.000000 118.96552 57.50000
## 33 15.6 10000 6800 2000 323000 3.400000 161.50000 47.33333
## 34 15.4 10200 7600 1700 208000 4.470588 122.35294 49.50000
## SII_1C Prot_2C Alb_2C Hb_2C Leucoc_2C Neutr_2C Linf_2C Plaq_2C
## 1 1383750.0 7.900000 4.500000 16.50000 6400.00 3400.000 2300.000 253000.0
## 2 980000.0 6.100000 3.700000 11.40000 8300.00 6200.000 1200.000 126000.0
## 3 1222400.0 7.200000 4.400000 16.70000 8400.00 4500.000 3000.000 329000.0
## 4 585200.0 7.200000 4.100000 15.30000 7200.00 4300.000 1900.000 254000.0
## 5 575354.8 8.000000 4.500000 16.30000 9200.00 5100.000 2800.000 313000.0
## 6 970562.5 8.100000 4.500000 15.50000 8000.00 5300.000 1800.000 285.0
## 7 775111.1 7.200000 4.100000 12.40000 8200.00 6400.000 1100.000 265000.0
## 8 276555.6 7.223333 4.012903 13.15312 9106.25 5796.875 2090.625 305883.9
## 9 1585517.2 7.223333 3.700000 13.40000 19400.00 16100.000 2300.000 406000.0
## 10 1103789.5 7.500000 4.100000 13.40000 8700.00 5500.000 2200.000 226000.0
## 11 4815200.0 6.500000 2.900000 8.60000 14500.00 12100.000 1200.000 858000.0
## 12 308758.6 6.800000 3.900000 11.40000 9400.00 4400.000 3100.000 260000.0
## 13 778444.4 7.100000 4.200000 15.00000 10200.00 5100.000 2900.000 319000.0
## 14 2006880.0 7.200000 4.000000 10.90000 14700.00 9900.000 3500.000 408000.0
## 15 2284800.0 7.200000 3.900000 11.20000 10600.00 7900.000 1400.000 254000.0
## 16 1545741.9 7.200000 3.900000 13.30000 9900.00 6100.000 2500.000 297000.0
## 17 1065428.6 5.300000 3.000000 10.30000 3800.00 2300.000 800.000 218000.0
## 18 760000.0 8.800000 4.100000 12.90000 11200.00 6100.000 3300.000 272000.0
## 19 522363.6 6.700000 3.700000 11.60000 4000.00 1800.000 1500.000 394000.0
## 20 3448750.0 7.900000 4.600000 12.30000 8600.00 6300.000 1200.000 425000.0
## 21 1191562.5 6.900000 4.400000 10.40000 12500.00 8500.000 1500.000 217000.0
## 22 776888.9 7.700000 3.900000 13.40000 6400.00 3600.000 1800.000 194000.0
## 23 747272.7 7.800000 3.600000 15.80000 5400.00 3700.000 1000.000 237000.0
## 24 377727.3 7.400000 4.000000 13.20000 5100.00 2400.000 2100.000 240000.0
## 25 1263888.9 7.500000 3.800000 11.40000 13900.00 7900.000 3900.000 615000.0
## 26 3598875.0 7.223333 4.012903 13.15312 9106.25 5796.875 2090.625 305883.9
## 27 324000.0 6.800000 4.200000 13.50000 5300.00 3300.000 1400.000 235000.0
## 28 2546833.3 7.100000 4.000000 11.70000 6900.00 5900.000 600.000 259000.0
## 29 888857.1 7.500000 3.700000 13.80000 12000.00 5700.000 4000.000 256000.0
## 30 1156272.7 6.300000 4.100000 13.00000 8300.00 4100.000 2900.000 343000.0
## 31 2693250.0 7.223333 4.012903 11.40000 7600.00 4900.000 1300.000 412000.0
## 32 1035000.0 7.500000 4.500000 12.90000 8800.00 5800.000 1800.000 337000.0
## 33 1098200.0 7.700000 4.300000 15.70000 9600.00 5900.000 2200.000 312000.0
## 34 929882.4 6.600000 4.100000 16.30000 8900.00 5000.000 2400.000 254000.0
## NLR_2C NLR2C_corte4o5 PLR_2C PNI_2C SII_2C primera_eval
## 1 1.478261 0.00 110.0000000 56.50000 374000.0000 EE
## 2 5.166667 1.00 105.0000000 43.00000 651000.0000 RP
## 3 1.500000 0.00 109.6666667 59.00000 493500.0000 RP
## 4 2.263158 0.00 133.6842105 50.50000 574842.1053 PS
## 5 1.821429 0.00 111.7857143 59.00000 570107.1429 EE
## 6 2.944444 0.00 0.1583333 54.00000 839.1667 RP
## 7 5.818182 1.00 240.9090909 46.50000 1541818.1818 EE
## 8 3.348731 0.25 177.5906414 50.70968 1134689.6890 RP
## 9 7.000000 1.00 176.5217391 48.50000 2842000.0000 EE
## 10 2.500000 0.00 102.7272727 52.00000 565000.0000 RP
## 11 10.083333 1.00 715.0000000 35.00000 8651500.0000 PE
## 12 1.419355 0.00 83.8709677 54.50000 369032.2581 EE
## 13 1.758621 0.00 110.0000000 56.50000 561000.0000 RP
## 14 2.828571 0.00 116.5714286 57.50000 1154057.1429 EE
## 15 5.642857 1.00 181.4285714 46.00000 1433285.7143 EE
## 16 2.440000 0.00 118.8000000 51.50000 724680.0000 RP
## 17 2.875000 0.00 272.5000000 34.00000 626750.0000 EE
## 18 1.848485 0.00 82.4242424 57.50000 502787.8788 RP
## 19 1.200000 0.00 262.6666667 44.50000 472800.0000 RP
## 20 5.250000 1.00 354.1666667 52.00000 2231250.0000 EE
## 21 5.666667 1.00 144.6666667 51.50000 1229666.6667 PE
## 22 2.000000 0.00 107.7777778 48.00000 388000.0000 EE
## 23 3.700000 0.00 237.0000000 41.00000 876900.0000 RP
## 24 1.142857 0.00 114.2857143 50.50000 274285.7143 EE
## 25 2.025641 0.00 157.6923077 57.50000 1245769.2308 EE
## 26 3.348731 0.25 177.5906414 50.70968 1134689.6890 PE
## 27 2.357143 0.00 167.8571429 49.00000 553928.5714 RP
## 28 9.833333 1.00 431.6666667 43.00000 2546833.3333 PE
## 29 1.425000 0.00 64.0000000 57.00000 364800.0000 EE
## 30 1.413793 0.00 118.2758621 55.50000 484931.0345 EE
## 31 3.769231 0.00 316.9230769 50.70968 1552923.0769 PE
## 32 3.222222 0.00 187.2222222 54.00000 1085888.8889 RP
## 33 2.681818 0.00 141.8181818 54.00000 836727.2727 RP
## 34 2.083333 0.00 105.8333333 53.00000 529166.6667 EE
## Prot_1eval Alb_1eval Hb_1eval Leucoc_1eval Neutr_1eval Linf_1eval Plaq_1eval
## 1 7.300000 4.4 16.9 8000 5300 2100 262000
## 2 6.000000 3.9 11.2 7500 5500 1300 96000
## 3 7.100000 4.5 16.6 8700 4900 2900 315000
## 4 7.200000 4.0 15.7 7800 4400 2500 259000
## 5 7.087097 4.3 16.5 8700 4600 2800 285000
## 6 7.600000 4.4 15.4 8000 5900 1400 263000
## 7 6.700000 3.9 11.1 7600 6000 1000 229000
## 8 6.400000 4.2 11.6 8600 6300 1400 124000
## 9 6.900000 3.7 12.9 16200 13200 1900 317000
## 10 7.700000 4.5 14.6 7400 4700 1900 219000
## 11 7.000000 3.1 8.8 10200 9100 500 527000
## 12 7.200000 4.0 10.8 11100 7200 2600 227000
## 13 7.100000 4.2 15.1 9100 5000 2900 308000
## 14 8.000000 4.5 12.9 18400 13600 3200 328000
## 15 7.087097 3.8 11.3 9400 7200 900 309000
## 16 7.000000 4.1 15.8 9800 6000 2600 205000
## 17 5.500000 3.6 13.7 4600 2600 1100 220000
## 18 8.500000 4.1 12.7 10200 5400 3100 282000
## 19 7.100000 3.9 12.2 3100 1400 1300 290000
## 20 7.300000 3.7 12.5 9200 7100 1100 400000
## 21 6.400000 3.9 9.9 10000 7500 800 216000
## 22 7.700000 3.9 13.4 6400 3600 1800 194000
## 23 7.087097 3.1 14.9 4500 2900 1000 220000
## 24 7.700000 4.1 13.8 4300 2200 1600 234000
## 25 7.800000 3.9 11.8 13900 7700 4000 647000
## 26 6.400000 3.7 11.7 9000 6300 800 457000
## 27 7.000000 4.2 13.8 4600 3100 1100 257000
## 28 7.100000 4.0 11.7 6900 5900 600 259000
## 29 6.900000 3.9 14.5 9100 4200 3500 199000
## 30 6.300000 4.1 13.0 8300 4100 2900 343000
## 31 7.000000 4.0 11.3 7300 4300 1800 353000
## 32 7.700000 4.6 12.9 9700 6500 2100 308000
## 33 7.500000 4.3 15.9 8700 6000 1600 320000
## 34 6.600000 4.1 16.3 8900 5000 2400 254000
## NLR_1eval PLR_1eval PNI_1eval SII_1eval Mejor_resp N_ciclos segunda_eval
## 1 2.523810 124.76190 54.5 661238.1 RC 35 0.5185185
## 2 4.230769 73.84615 45.5 406153.8 RC 35 0.0000000
## 3 1.689655 108.62069 59.5 532241.4 RP 7 0.0000000
## 4 1.760000 103.60000 52.5 455840.0 EE 11 1.0000000
## 5 1.642857 101.78571 57.0 468214.3 EE 7 1.0000000
## 6 4.214286 187.85714 51.0 1108357.1 RC 4 0.5185185
## 7 6.000000 229.00000 44.0 1374000.0 RP 19 1.0000000
## 8 4.500000 88.57143 49.0 558000.0 RP 1 0.0000000
## 9 6.947368 166.84211 46.5 2202315.8 EE 3 0.0000000
## 10 2.473684 115.26316 54.5 541736.8 RP 26 0.0000000
## 11 18.200000 1054.00000 33.5 9591400.0 PE 3 1.0000000
## 12 2.769231 87.30769 53.0 628615.4 RP 5 0.0000000
## 13 1.724138 106.20690 56.5 531034.5 RP 11 1.0000000
## 14 4.250000 102.50000 61.0 1394000.0 EE 6 0.0000000
## 15 8.000000 343.33333 42.5 2472000.0 EE 6 1.0000000
## 16 2.307692 78.84615 54.0 473076.9 RP 32 1.0000000
## 17 2.363636 200.00000 41.5 520000.0 RP 25 0.5185185
## 18 1.741935 90.96774 56.5 491225.8 RP 35 0.5185185
## 19 1.076923 223.07692 45.5 312307.7 RP 16 0.0000000
## 20 6.454545 363.63636 42.5 2581818.2 RC 25 0.0000000
## 21 9.375000 270.00000 43.0 2025000.0 PE 3 0.0000000
## 22 2.000000 107.77778 48.0 388000.0 RP 5 1.0000000
## 23 2.900000 220.00000 36.0 638000.0 RP 8 0.5185185
## 24 1.375000 146.25000 49.0 321750.0 EE 8 1.0000000
## 25 1.925000 161.75000 59.0 1245475.0 EE 8 1.0000000
## 26 7.875000 571.25000 41.0 3598875.0 PE 1 1.0000000
## 27 2.818182 233.63636 47.5 724272.7 RC 35 0.0000000
## 28 9.833333 431.66667 43.0 2546833.3 PE 2 0.0000000
## 29 1.200000 56.85714 56.5 238800.0 RP 27 0.0000000
## 30 1.413793 118.27586 55.5 484931.0 RP 13 1.0000000
## 31 2.388889 196.11111 49.0 843277.8 PE 4 1.0000000
## 32 3.095238 146.66667 56.5 953333.3 RP 35 0.5185185
## 33 3.750000 200.00000 51.0 1200000.0 RP 23 1.0000000
## 34 2.083333 105.83333 53.0 529166.7 RP 35 0.5185185
## Exitus SLP SLP_cens SG SG_cens
## 1 1 29.8644764 1 29.864476 1
## 2 0 60.3860370 1 60.386037 1
## 3 0 35.1868583 0 57.626283 1
## 4 1 7.3921971 0 33.741273 0
## 5 1 4.5010267 0 18.825462 0
## 6 0 41.4948665 1 41.494867 1
## 7 1 24.0164271 0 30.225873 0
## 8 1 7.8850103 1 7.885010 1
## 9 1 1.8069815 0 1.806982 0
## 10 1 19.9425051 1 19.942505 0
## 11 1 1.8726899 0 17.478439 0
## 12 1 40.7392197 1 40.739220 0
## 13 1 7.4579055 0 41.002053 0
## 14 1 5.6509240 0 8.837782 0
## 15 1 3.6796715 0 6.570842 0
## 16 1 22.3737166 0 28.747433 0
## 17 1 21.9794661 1 21.979466 0
## 18 0 46.3244353 1 46.324435 1
## 19 0 35.3182752 0 35.318275 1
## 20 0 45.6344969 1 45.634497 1
## 21 1 1.9055441 0 5.749487 0
## 22 1 7.2607803 0 22.078029 0
## 23 1 9.3305955 1 9.330595 0
## 24 1 7.1293634 0 16.131417 0
## 25 0 5.6180698 0 10.611910 0
## 26 1 0.7556468 0 41.166324 0
## 27 0 31.1457906 1 31.145791 1
## 28 1 1.3798768 0 1.839836 0
## 29 1 17.8069815 0 26.579055 0
## 30 1 11.1704312 0 22.702259 0
## 31 1 1.8069815 0 16.000000 0
## 32 0 40.2135524 1 40.213552 1
## 33 1 16.1642710 0 35.778234 0
## 34 0 39.4579055 1 39.457906 1df_imputado1$Edad_dx <- round(df_imputado1$Edad_dx, 0)
df_imputado1$LDH <- round(df_imputado1$LDH, 0)
df_imputado1$LDH <- round(df_imputado1$LDH, 0)
df_imputado1$Exp_tab <- round(df_imputado1$Exp_tab, 0)
df_imputado1$Col_total <- round(df_imputado1$Col_total, 0)
df_imputado1$Leucoc_1C <- round(df_imputado1$Leucoc_1C, 0)
df_imputado1$Neutr_1C <- round(df_imputado1$Neutr_1C, 0)
df_imputado1$Linf_1C <- round(df_imputado1$Linf_1C, 0)
df_imputado1$Plaq_1C <- round(df_imputado1$Plaq_1C, 0)
df_imputado1$Prot_1C <- round(df_imputado1$Prot_1C, 1)
df_imputado1$Alb_1C <- round(df_imputado1$Alb_1C, 1)
df_imputado1$Hb_1C <- round(df_imputado1$Hb_1C, 1)
df_imputado1$Prot_tot <- round(df_imputado1$Prot_tot, 1)
df_imputado1$Albumina <- round(df_imputado1$Albumina, 1)
df_imputado1$Porcentaje_perdpeso <- round(df_imputado1$Porcentaje_perdpeso, 4)
df_imputado1$NLR_pre <- round(df_imputado1$NLR_pre, 2)
df_imputado1$PLR_pre <- round(df_imputado1$PLR_pre, 2)
df_imputado1$PNI_pre <- round(df_imputado1$PNI_pre, 2)
df_imputado1$ALI_pre <- round(df_imputado1$ALI_pre, 2)
df_imputado1$SII_pre <- round(df_imputado1$SII_pre, 2)
df_imputado1$NLR_1C <- round(df_imputado1$NLR_1C, 2)
df_imputado1$PLR_2C <- round(df_imputado1$PLR_2C, 2)
df_imputado1$SII_2C <- round(df_imputado1$SII_2C, 2)3.2 Cart method:
imputed_data2 <- mice(df %>%
select(Idpac,Histologia,Afectacion_ganglionar,Afectacion_metastasica,Estadio,Estatinas,primera_eval_num,Mejor_resp_num,Tipo_tox,
Tamaño_tumor,Grado_tox,Motivo_inter, NLR1C_corte4, NLR1C_corte5, Histología_num, Estadio_num, Toxicidad,Interrupc_tto,
Enf_neurod,Sexo, ECOG, Progresion, Cardiop, Diabetes),
method = "cart", print = FALSE)## Warning: Number of logged events: 150df_imputado2 <- complete(imputed_data2)
df_imputado2## Idpac Histologia Afectacion_ganglionar Afectacion_metastasica
## 1 P_01 Adenocarcinoma 2 1c
## 2 P_02 Otros 2 1c
## 3 P_03 Adenocarcinoma 1 1c
## 4 P_04 Escamoso 2 0
## 5 P_05 Escamoso 2 1a
## 6 P_06 Otros 3 1c
## 7 P_07 Escamoso 2 1c
## 8 P_08 Escamoso 2 0
## 9 P_09 Escamoso 2 0
## 10 P_10 Adenocarcinoma 2 1c
## 11 P_11 Adenocarcinoma 3 1c
## 12 P_12 Adenocarcinoma 1 1b
## 13 P_13 Adenocarcinoma 3 1a
## 14 P_14 Otros 0 1b
## 15 P_15 Adenocarcinoma 0 1c
## 16 P_16 Adenocarcinoma 2 1b
## 17 P_18 Adenocarcinoma 2 1c
## 18 P_19 Adenocarcinoma 3 1c
## 19 P_20 Ca. indiferenciado 2 1c
## 20 P_22 Adenocarcinoma x 1a
## 21 P_23 Adenocarcinoma 0 1c
## 22 P_24 Escamoso 2 1c
## 23 P_25 Adenocarcinoma 3 1c
## 24 P_26 Adenocarcinoma 2 1c
## 25 P_27 Adenocarcinoma 3 1c
## 26 P_28 Adenocarcinoma 3 1c
## 27 P_29 Otros 3 1b
## 28 P_30 Adenocarcinoma 3 1b
## 29 P_31 Adenocarcinoma 2 1a
## 30 P_32 Adenocarcinoma 3 1c
## 31 P_33 Adenocarcinoma 2 1b
## 32 P_34 Otros 3 0
## 33 P_35 Adenocarcinoma 2 1c
## 34 P_36 Adenocarcinoma 0 1c
## Estadio Estatinas primera_eval_num Mejor_resp_num Tipo_tox
## 1 IVB 0 2 0 Miocarditis
## 2 IVB 0 1 0 Dermatitis
## 3 IVB 1 1 1 Hepatitis
## 4 IIIB 1 2 2 0
## 5 IVA 0 2 2 0
## 6 IVB 0 1 0 Uveítis
## 7 IVB 1 2 1 Neumonitis
## 8 IIIA 0 1 1 Hepatitis
## 9 IIIB 1 2 2 0
## 10 IVB 0 1 1 Uveítis
## 11 IVB 0 3 3 0
## 12 IVA 1 2 1 Neumonitis
## 13 IVA 0 1 1 Queratitis/Dermatitis
## 14 IVA 0 2 2 0
## 15 IVB 0 2 2 Dermatitis
## 16 IVB 0 1 1 Artritis
## 17 IVB 0 2 1 0
## 18 IVB 0 1 1 Tiroiditis
## 19 IVB 0 1 1 Encefalitis
## 20 IVA 0 1 0 Neumonitis
## 21 IVB 1 3 3 0
## 22 IVB 0 2 1 Neumonitis
## 23 IVB 0 1 1 0
## 24 IVB 0 2 2 0
## 25 IVB 0 (fibrato) 1 1 0
## 26 IVB 1 3 3 0
## 27 IVB 0 1 0 Tiroiditis
## 28 IVB 0 3 3 0
## 29 IVA 0 3 2 Dermatitis
## 30 IVB 0 2 1 Dermatitis
## 31 IVB 0 3 3 0
## 32 IIIC 1 1 1 0
## 33 IVB 1 1 1 0
## 34 IVB 0 2 1 Artritis
## Tamaño_tumor Grado_tox Motivo_inter NLR1C_corte4
## 1 2b 3 Fin del tratamiento previsto 0
## 2 X 1 Fin del tratamiento previsto 1
## 3 2b 3 Toxicidad 0
## 4 4 0 Progresión 0
## 5 2a 0 Progresión 0
## 6 x 2 Toxicidad 0
## 7 3 3 Toxicidad 0
## 8 1c 3 Toxicidad 0
## 9 4 0 Exitus 1
## 10 3 1 Exitus (otra causa) 1
## 11 4 0 Progresión 1
## 12 2b 3 Toxicidad 0
## 13 4 1 Progresión 0
## 14 x 0 Progresión 1
## 15 4 1 Progresión 1
## 16 x 1 Progresión 0
## 17 2b 0 Exitus (otra causa) 1
## 18 4 1 Fin del tratamiento previsto 0
## 19 4 3 Toxicidad 0
## 20 x 2 Toxicidad 1
## 21 3 0 Progresión 1
## 22 3 3 Toxicidad 0
## 23 3 0 2º tumor/ hepatocarcinoma 0
## 24 4 0 Progresión 0
## 25 4 0 Progresión 0
## 26 4 0 Progresión 1
## 27 4 2 Fin del tratamiento previsto 0
## 28 4 0 Progresión 1
## 29 4 3 Toxicidad 0
## 30 4 1 Progresión 0
## 31 4 0 Progresión 0
## 32 3 0 Fin del tratamiento previsto 0
## 33 4 0 Progresión 0
## 34 4 G2 Fin del tratamiento previsto 1
## NLR1C_corte5 Histología_num Estadio_num Toxicidad Interrupc_tto Enf_neurod
## 1 0 0 4 1 1 0
## 2 1 2 4 1 1 0
## 3 0 0 4 1 1 0
## 4 0 1 3 0 1 0
## 5 0 1 4 0 1 0
## 6 0 2 4 1 1 0
## 7 0 1 4 1 1 0
## 8 0 1 3 1 1 1
## 9 0 1 3 0 1 1
## 10 1 0 4 1 1 0
## 11 1 0 4 0 1 0
## 12 0 0 4 0 1 0
## 13 0 0 4 1 1 0
## 14 0 2 4 0 1 0
## 15 1 0 4 1 1 0
## 16 0 0 4 1 1 0
## 17 0 0 4 0 1 0
## 18 0 0 4 1 1 0
## 19 0 2 4 1 1 0
## 20 1 0 4 1 1 0
## 21 1 0 4 0 1 1
## 22 0 1 4 1 1 0
## 23 0 0 4 0 1 0
## 24 0 0 4 0 1 0
## 25 0 0 4 0 1 0
## 26 1 0 4 0 1 0
## 27 0 2 4 1 1 0
## 28 1 0 4 0 1 0
## 29 0 0 4 1 1 0
## 30 0 0 4 1 1 0
## 31 0 0 4 0 1 0
## 32 0 2 3 0 1 0
## 33 0 0 4 0 0 0
## 34 0 0 4 1 1 0
## Sexo ECOG Progresion Cardiop Diabetes
## 1 2 1 0 0 0
## 2 1 2 0 0 0
## 3 2 0 1 0 0
## 4 2 0 1 1 0
## 5 2 1 1 0 0
## 6 2 1 0 0 0
## 7 1 1 1 0 1
## 8 2 2 0 1 0
## 9 2 1 1 1 0
## 10 2 1 0 0 0
## 11 2 2 1 0 0
## 12 2 1 0 1 0
## 13 1 1 1 0 1
## 14 2 1 1 0 0
## 15 1 2 1 0 0
## 16 2 1 1 0 0
## 17 1 0 0 0 0
## 18 2 1 0 0 0
## 19 1 1 1 0 0
## 20 2 0 0 0 0
## 21 2 2 1 0 1
## 22 2 1 1 0 0
## 23 2 1 0 0 0
## 24 1 1 1 0 0
## 25 2 1 1 0 0
## 26 1 1 1 0 0
## 27 1 1 0 0 0
## 28 2 1 1 0 0
## 29 2 1 1 0 0
## 30 2 1 1 0 0
## 31 2 1 1 0 0
## 32 2 0 0 0 1
## 33 1 2 1 0 0
## 34 2 1 0 0 0redondear = c("Idpac","Histologia","Afectacion_ganglionar","Afectacion_metastasica","Estadio","Estatinas","primera_eval_num","Mejor_resp_num",
"Tipo_tox","Tamaño_tumor","Grado_tox","Motivo_inter","NLR1C_corte4","NLR1C_corte5","Histología_num","Estadio_num","Toxicidad","Interrupc_tto",
"Enf_neurod","Sexo","ECOG","Progresion","Cardiop","Diabetes")
sapply(df_imputado2[redondear], class)## Idpac Histologia Afectacion_ganglionar
## "factor" "factor" "factor"
## Afectacion_metastasica Estadio Estatinas
## "factor" "factor" "factor"
## primera_eval_num Mejor_resp_num Tipo_tox
## "factor" "factor" "factor"
## Tamaño_tumor Grado_tox Motivo_inter
## "factor" "factor" "factor"
## NLR1C_corte4 NLR1C_corte5 Histología_num
## "factor" "factor" "factor"
## Estadio_num Toxicidad Interrupc_tto
## "factor" "factor" "factor"
## Enf_neurod Sexo ECOG
## "factor" "factor" "factor"
## Progresion Cardiop Diabetes
## "factor" "factor" "factor"df_imputado2[redondear] <- lapply(df_imputado2[redondear], as.numeric)
df_imputado2[redondear] <- round(df_imputado2[redondear], 0)df_imputado2 <- lapply(df_imputado2, as.factor)df_completo <- cbind(df_imputado1, df_imputado2)3.3 Create variables response as factor/numerical:
asignar_valor_primera_eval <- function(valor) {
if (valor == "RP") {
return(1)
} else if (valor %in% c("PS", "EE")) {
return(2)
} else if (valor == "PE") {
return(3)
} else {
return(NA)
}
}
df_completo <- df_completo %>%
mutate(pri_eval_num_ok = sapply(primera_eval, asignar_valor_primera_eval))asignar_valor_mejor_resp <- function(valor) {
if (valor == "RC") {
return(0)
} else if (valor == "RP") {
return(1)
} else if (valor == "EE") {
return(2)
} else if (valor == "PE") {
return(3)
} else {
return(NA) # Manejo de otros valores, si es necesario
}
}
df_completo <- df_completo %>%
mutate(mejor_resp_num_ok = sapply(Mejor_resp, asignar_valor_mejor_resp))4 ANÁLISIS DESCRIPTIVO:
columnas_numericas <- sapply(df_completo, is.numeric)
for (columna in names(df_completo[columnas_numericas])) {
cat("Variable:", columna, "\n")
cat("Summary:\n")
print(summary(df_completo[[columna]]))
cat("Histogram:\n")
hist(df_completo[[columna]], main = paste("Histogram of", columna), xlab = columna)
cat("Boxplot:\n")
boxplot(df_completo[[columna]], main = paste("Boxplot of", columna))
cat("Density graph:\n")
plot(density(df_completo[[columna]]), main = paste("Density of", columna))
cat("\n")
}## Variable: Edad_dx
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 46.00 60.00 65.50 65.35 71.00 82.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Anciano
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.3529 1.0000 1.0000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Peso
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 47.00 62.25 67.00 70.16 77.28 102.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Talla
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.500 1.593 1.630 1.656 1.728 1.910
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: IMC
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 18.36 22.53 25.11 25.57 28.21 35.63
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Porcentaje_perdpeso
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00000 0.00000 0.03450 0.04584 0.07300 0.22900
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Exp_tab
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 37.00 50.00 51.68 60.00 200.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PD_L1
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.00 70.00 80.00 78.88 93.75 100.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Col_total
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 111.0 153.2 189.0 187.4 205.0 397.0
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: LDH
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 156.0 184.0 200.0 263.7 264.0 1644.0
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Prot_tot
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.400 6.900 7.000 7.006 7.300 8.900
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Albumina
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.800 3.700 4.000 3.912 4.200 4.400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Hb
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.60 11.95 13.00 13.16 14.07 16.70
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Leucoc_tot
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4000 7625 9850 10012 12300 20500
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Neutrofilos
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2500 5075 7200 7162 8700 13400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Linf_tot
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 400 1125 1500 1650 2150 3500
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Plaquetas
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 112000 229500 283000 298941 337250 709000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: NLR_pre
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.670 2.925 3.830 5.940 6.060 24.600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PLR_pre
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 71.5 131.7 177.2 232.9 251.0 928.0
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PNI_pre
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 32.00 45.50 48.75 47.42 50.88 59.50
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: ALI_pre
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.20 14.64 26.42 26.86 32.73 67.80
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SII_pre
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 250250 907950 1076325 1689960 1905679 8723200
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Prot_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.600 6.800 7.050 7.044 7.375 9.100
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Alb_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.100 3.700 3.950 3.906 4.100 4.600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Hb_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 8.40 11.60 12.30 12.89 14.50 16.10
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Leucoc_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3600 7325 9100 9435 12375 16100
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Neutr_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1700 4450 6250 6318 8300 12100
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Linf_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 600 1100 1750 1894 2725 3600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Plaq_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 112000 246250 330500 336206 428500 650000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: NLR_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.280 2.095 3.255 4.040 5.048 10.400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PLR_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 83.45 127.03 160.43 211.81 250.80 571.25
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PNI_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 10.00 43.00 49.25 47.33 53.88 60.50
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SII_1C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 276556 763778 1050214 1341856 1505244 4815200
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Prot_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.300 6.950 7.212 7.223 7.500 8.800
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Alb_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 2.900 3.900 4.013 4.013 4.200 4.600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Hb_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 8.60 11.45 13.15 13.15 14.70 16.70
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Leucoc_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3800 7300 8750 9106 10125 19400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Neutr_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1800 4325 5600 5797 6175 16100
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Linf_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 600 1400 2091 2091 2725 4000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Plaq_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 285 243250 268500 305884 335000 858000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: NLR_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.143 1.828 2.591 3.349 3.752 10.083
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: NLR2C_corte4o5
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 0.25 0.25 1.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PLR_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.16 109.75 137.75 177.59 185.77 715.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PNI_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 34.00 48.12 51.50 50.71 55.25 59.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SII_2C
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 839 495822 638875 1134690 1210764 8651500
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Prot_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 5.500 6.900 7.094 7.087 7.450 8.500
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Alb_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3.100 3.900 4.000 4.018 4.200 4.600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Hb_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 8.80 11.70 12.95 13.33 15.05 16.90
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Leucoc_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 3100 7425 8700 8682 9625 18400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Neutr_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1400 4325 5450 5726 6450 13600
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Linf_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 500 1100 1800 1897 2600 4000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Plaq_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 96000 221750 262500 286059 316500 647000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: NLR_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.077 1.801 2.647 4.027 4.438 18.200
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PLR_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 56.86 104.16 146.46 203.41 222.31 1054.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: PNI_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 33.50 44.38 50.00 49.66 55.25 61.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SII_1eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 238800 486505 633308 1265920 1341869 9591400
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: N_ciclos
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.00 5.00 9.50 15.26 25.75 35.00
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: segunda_eval
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.5185 0.5185 1.0000 1.0000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: Exitus
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 1.0000 0.7059 1.0000 1.0000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SLP
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.7557 5.6263 13.6674 19.2545 34.1766 60.3860
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SLP_cens
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.3824 1.0000 1.0000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SG
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.807 16.033 27.663 26.859 40.025 60.386
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: SG_cens
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.3235 1.0000 1.0000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: pri_eval_num_ok
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.000 1.000 2.000 1.765 2.000 3.000
## Histogram:
## Boxplot:
## Density graph:
##
## Variable: mejor_resp_num_ok
## Summary:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 1.000 1.000 1.353 2.000 3.000
## Histogram:
## Boxplot:
## Density graph:
columnas_categoricas <- sapply(df_completo, is.factor)
for (columna in names(df_completo[columnas_categoricas])) {
cat("Variable:", columna, "\n")
cat("Frequency:\n")
print(table(df_completo[[columna]]))
cat("Bar graphic:\n")
barplot(table(df_completo[[columna]]), main = paste("Bar graphic of", columna))
cat("Pie chart:\n")
pie(table(df_completo[[columna]]), main = paste("Pie chart of", columna))
cat("\n")
}## Variable: Idpac
## Frequency:
##
## 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26
## 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
## 27 28 29 30 31 32 33 34
## 1 1 1 1 1 1 1 1
## Bar graphic:
## Pie chart:
##
## Variable: Histologia
## Frequency:
##
## 1 2 3 4
## 22 1 6 5
## Bar graphic:
## Pie chart:
##
## Variable: Afectacion_ganglionar
## Frequency:
##
## 1 2 3 4 5
## 4 2 16 11 1
## Bar graphic:
## Pie chart:
##
## Variable: Afectacion_metastasica
## Frequency:
##
## 1 2 3 4
## 4 4 6 20
## Bar graphic:
## Pie chart:
##
## Variable: Estadio
## Frequency:
##
## 1 2 3 4 5
## 1 2 1 6 24
## Bar graphic:
## Pie chart:
##
## Variable: Estatinas
## Frequency:
##
## 1 2 3
## 24 1 9
## Bar graphic:
## Pie chart:
##
## Variable: primera_eval_num
## Frequency:
##
## 1 2 3
## 15 13 6
## Bar graphic:
## Pie chart:
##
## Variable: Mejor_resp_num
## Frequency:
##
## 1 2 3 4
## 5 17 7 5
## Bar graphic:
## Pie chart:
##
## Variable: Tipo_tox
## Frequency:
##
## 1 2 3 4 5 6 7 8 9 10
## 15 2 4 1 2 1 4 1 2 2
## Bar graphic:
## Pie chart:
##
## Variable: Tamaño_tumor
## Frequency:
##
## 1 2 3 4 5 6 7
## 1 1 4 6 17 4 1
## Bar graphic:
## Pie chart:
##
## Variable: Grado_tox
## Frequency:
##
## 1 2 3 4 5
## 15 7 3 8 1
## Bar graphic:
## Pie chart:
##
## Variable: Motivo_inter
## Frequency:
##
## 1 2 3 4 5 6
## 1 1 2 6 15 9
## Bar graphic:
## Pie chart:
##
## Variable: NLR1C_corte4
## Frequency:
##
## 1 2
## 22 12
## Bar graphic:
## Pie chart:
##
## Variable: NLR1C_corte5
## Frequency:
##
## 1 2
## 26 8
## Bar graphic:
## Pie chart:
##
## Variable: Histología_num
## Frequency:
##
## 1 2 3
## 22 6 6
## Bar graphic:
## Pie chart:
##
## Variable: Estadio_num
## Frequency:
##
## 1 2
## 4 30
## Bar graphic:
## Pie chart:
##
## Variable: Toxicidad
## Frequency:
##
## 1 2
## 16 18
## Bar graphic:
## Pie chart:
##
## Variable: Interrupc_tto
## Frequency:
##
## 1 2
## 1 33
## Bar graphic:
## Pie chart:
##
## Variable: Enf_neurod
## Frequency:
##
## 1 2
## 31 3
## Bar graphic:
## Pie chart:
##
## Variable: Sexo
## Frequency:
##
## 1 2
## 10 24
## Bar graphic:
## Pie chart:
##
## Variable: ECOG
## Frequency:
##
## 1 2 3
## 5 23 6
## Bar graphic:
## Pie chart:
##
## Variable: Progresion
## Frequency:
##
## 1 2
## 13 21
## Bar graphic:
## Pie chart:
##
## Variable: Cardiop
## Frequency:
##
## 1 2
## 30 4
## Bar graphic:
## Pie chart:
##
## Variable: Diabetes
## Frequency:
##
## 1 2
## 30 4
## Bar graphic:
## Pie chart:
# ruta_archivo <- "C:/Users/magob/Desktop/PROYECTO/df_definitivo.xlsx"
#
# write.xlsx(df_completo, file = ruta_archivo, rowNames = TRUE)
#
# if (file.exists(ruta_archivo)) {
# cat("¡Los datos se han guardado exitosamente en", ruta_archivo, "!\n")
# } else {
# cat("Hubo un problema al guardar los datos. Por favor, verifica la ruta y el nombre del archivo.\n")
# }